iliabel commited on
Commit
8dbd5c8
1 Parent(s): 47856a6

Upload PPO LunarLander-v2 trained agent

Browse files
README.md CHANGED
@@ -16,7 +16,7 @@ model-index:
16
  type: LunarLander-v2
17
  metrics:
18
  - type: mean_reward
19
- value: 256.45 +/- 18.73
20
  name: mean_reward
21
  verified: false
22
  ---
 
16
  type: LunarLander-v2
17
  metrics:
18
  - type: mean_reward
19
+ value: 289.50 +/- 16.81
20
  name: mean_reward
21
  verified: false
22
  ---
config.json CHANGED
@@ -1 +1 @@
1
- {"policy_class": {":type:": "<class 'abc.ABCMeta'>", ":serialized:": "gAWVOwAAAAAAAACMIXN0YWJsZV9iYXNlbGluZXMzLmNvbW1vbi5wb2xpY2llc5SMEUFjdG9yQ3JpdGljUG9saWN5lJOULg==", "__module__": "stable_baselines3.common.policies", "__doc__": "\n Policy class for actor-critic algorithms (has both policy and value prediction).\n Used by A2C, PPO and the likes.\n\n :param observation_space: Observation space\n :param action_space: Action space\n :param lr_schedule: Learning rate schedule (could be constant)\n :param net_arch: The specification of the policy and value networks.\n :param activation_fn: Activation function\n :param ortho_init: Whether to use or not orthogonal initialization\n :param use_sde: Whether to use State Dependent Exploration or not\n :param log_std_init: Initial value for the log standard deviation\n :param full_std: Whether to use (n_features x n_actions) parameters\n for the std instead of only (n_features,) when using gSDE\n :param use_expln: Use ``expln()`` function instead of ``exp()`` to ensure\n a positive standard deviation (cf paper). It allows to keep variance\n above zero and prevent it from growing too fast. In practice, ``exp()`` is usually enough.\n :param squash_output: Whether to squash the output using a tanh function,\n this allows to ensure boundaries when using gSDE.\n :param features_extractor_class: Features extractor to use.\n :param features_extractor_kwargs: Keyword arguments\n to pass to the features extractor.\n :param share_features_extractor: If True, the features extractor is shared between the policy and value networks.\n :param normalize_images: Whether to normalize images or not,\n dividing by 255.0 (True by default)\n :param optimizer_class: The optimizer to use,\n ``th.optim.Adam`` by default\n :param optimizer_kwargs: Additional keyword arguments,\n excluding the learning rate, to pass to the optimizer\n ", "__init__": "<function ActorCriticPolicy.__init__ at 0x7eed58d5c280>", "_get_constructor_parameters": "<function ActorCriticPolicy._get_constructor_parameters at 0x7eed58d5c310>", "reset_noise": "<function ActorCriticPolicy.reset_noise at 0x7eed58d5c3a0>", "_build_mlp_extractor": "<function ActorCriticPolicy._build_mlp_extractor at 0x7eed58d5c430>", "_build": "<function ActorCriticPolicy._build at 0x7eed58d5c4c0>", "forward": "<function ActorCriticPolicy.forward at 0x7eed58d5c550>", "extract_features": "<function ActorCriticPolicy.extract_features at 0x7eed58d5c5e0>", "_get_action_dist_from_latent": "<function ActorCriticPolicy._get_action_dist_from_latent at 0x7eed58d5c670>", "_predict": "<function ActorCriticPolicy._predict at 0x7eed58d5c700>", "evaluate_actions": "<function ActorCriticPolicy.evaluate_actions at 0x7eed58d5c790>", "get_distribution": "<function ActorCriticPolicy.get_distribution at 0x7eed58d5c820>", "predict_values": "<function ActorCriticPolicy.predict_values at 0x7eed58d5c8b0>", "__abstractmethods__": "frozenset()", "_abc_impl": "<_abc._abc_data object at 0x7eed58ee9400>"}, "verbose": 1, "policy_kwargs": {}, "num_timesteps": 1015808, "_total_timesteps": 1000000, "_num_timesteps_at_start": 0, "seed": null, "action_noise": null, "start_time": 1711816044179086492, "learning_rate": 0.0003, "tensorboard_log": null, "_last_obs": {":type:": "<class 'numpy.ndarray'>", ":serialized:": "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"}, "_last_episode_starts": {":type:": "<class 'numpy.ndarray'>", ":serialized:": "gAWVgwAAAAAAAACMEm51bXB5LmNvcmUubnVtZXJpY5SMC19mcm9tYnVmZmVylJOUKJYQAAAAAAAAAAAAAAAAAAAAAAAAAAAAAACUjAVudW1weZSMBWR0eXBllJOUjAJiMZSJiIeUUpQoSwOMAXyUTk5OSv////9K/////0sAdJRiSxCFlIwBQ5R0lFKULg=="}, "_last_original_obs": null, "_episode_num": 0, "use_sde": false, "sde_sample_freq": -1, "_current_progress_remaining": -0.015808000000000044, "_stats_window_size": 100, "ep_info_buffer": {":type:": "<class 'collections.deque'>", ":serialized:": "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"}, "ep_success_buffer": {":type:": "<class 'collections.deque'>", ":serialized:": "gAWVIAAAAAAAAACMC2NvbGxlY3Rpb25zlIwFZGVxdWWUk5QpS2SGlFKULg=="}, "_n_updates": 248, "observation_space": {":type:": "<class 'gymnasium.spaces.box.Box'>", ":serialized:": "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", "dtype": "float32", "bounded_below": "[ True True True True True True True True]", "bounded_above": "[ True True True True True True True True]", "_shape": [8], "low": "[-90. -90. -5. -5. -3.1415927 -5.\n -0. -0. ]", "high": "[90. 90. 5. 5. 3.1415927 5.\n 1. 1. ]", "low_repr": "[-90. -90. -5. -5. -3.1415927 -5.\n -0. -0. ]", "high_repr": "[90. 90. 5. 5. 3.1415927 5.\n 1. 1. ]", "_np_random": null}, "action_space": {":type:": "<class 'gymnasium.spaces.discrete.Discrete'>", ":serialized:": "gAWV2wAAAAAAAACMGWd5bW5hc2l1bS5zcGFjZXMuZGlzY3JldGWUjAhEaXNjcmV0ZZSTlCmBlH2UKIwBbpSMFW51bXB5LmNvcmUubXVsdGlhcnJheZSMBnNjYWxhcpSTlIwFbnVtcHmUjAVkdHlwZZSTlIwCaTiUiYiHlFKUKEsDjAE8lE5OTkr/////Sv////9LAHSUYkMIBAAAAAAAAACUhpRSlIwFc3RhcnSUaAhoDkMIAAAAAAAAAACUhpRSlIwGX3NoYXBllCmMBWR0eXBllGgOjApfbnBfcmFuZG9tlE51Yi4=", "n": "4", "start": "0", "_shape": [], "dtype": "int64", "_np_random": null}, "n_envs": 16, "n_steps": 1024, "gamma": 0.999, "gae_lambda": 0.98, "ent_coef": 0.01, "vf_coef": 0.5, "max_grad_norm": 0.5, "batch_size": 64, "n_epochs": 4, "clip_range": {":type:": "<class 'function'>", ":serialized:": "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"}, "clip_range_vf": null, "normalize_advantage": true, "target_kl": null, "lr_schedule": {":type:": "<class 'function'>", ":serialized:": "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"}, "system_info": {"OS": "Linux-6.1.58+-x86_64-with-glibc2.35 # 1 SMP PREEMPT_DYNAMIC Sat Nov 18 15:31:17 UTC 2023", "Python": "3.10.12", "Stable-Baselines3": "2.0.0a5", "PyTorch": "2.2.1+cu121", "GPU Enabled": "True", "Numpy": "1.25.2", "Cloudpickle": "2.2.1", "Gymnasium": "0.28.1", "OpenAI Gym": "0.25.2"}}
 
1
+ {"policy_class": {":type:": "<class 'abc.ABCMeta'>", ":serialized:": "gAWVOwAAAAAAAACMIXN0YWJsZV9iYXNlbGluZXMzLmNvbW1vbi5wb2xpY2llc5SMEUFjdG9yQ3JpdGljUG9saWN5lJOULg==", "__module__": "stable_baselines3.common.policies", "__doc__": "\n Policy class for actor-critic algorithms (has both policy and value prediction).\n Used by A2C, PPO and the likes.\n\n :param observation_space: Observation space\n :param action_space: Action space\n :param lr_schedule: Learning rate schedule (could be constant)\n :param net_arch: The specification of the policy and value networks.\n :param activation_fn: Activation function\n :param ortho_init: Whether to use or not orthogonal initialization\n :param use_sde: Whether to use State Dependent Exploration or not\n :param log_std_init: Initial value for the log standard deviation\n :param full_std: Whether to use (n_features x n_actions) parameters\n for the std instead of only (n_features,) when using gSDE\n :param use_expln: Use ``expln()`` function instead of ``exp()`` to ensure\n a positive standard deviation (cf paper). It allows to keep variance\n above zero and prevent it from growing too fast. In practice, ``exp()`` is usually enough.\n :param squash_output: Whether to squash the output using a tanh function,\n this allows to ensure boundaries when using gSDE.\n :param features_extractor_class: Features extractor to use.\n :param features_extractor_kwargs: Keyword arguments\n to pass to the features extractor.\n :param share_features_extractor: If True, the features extractor is shared between the policy and value networks.\n :param normalize_images: Whether to normalize images or not,\n dividing by 255.0 (True by default)\n :param optimizer_class: The optimizer to use,\n ``th.optim.Adam`` by default\n :param optimizer_kwargs: Additional keyword arguments,\n excluding the learning rate, to pass to the optimizer\n ", "__init__": "<function ActorCriticPolicy.__init__ at 0x7eed58d5c280>", "_get_constructor_parameters": "<function ActorCriticPolicy._get_constructor_parameters at 0x7eed58d5c310>", "reset_noise": "<function ActorCriticPolicy.reset_noise at 0x7eed58d5c3a0>", "_build_mlp_extractor": "<function ActorCriticPolicy._build_mlp_extractor at 0x7eed58d5c430>", "_build": "<function ActorCriticPolicy._build at 0x7eed58d5c4c0>", "forward": "<function ActorCriticPolicy.forward at 0x7eed58d5c550>", "extract_features": "<function ActorCriticPolicy.extract_features at 0x7eed58d5c5e0>", "_get_action_dist_from_latent": "<function ActorCriticPolicy._get_action_dist_from_latent at 0x7eed58d5c670>", "_predict": "<function ActorCriticPolicy._predict at 0x7eed58d5c700>", "evaluate_actions": "<function ActorCriticPolicy.evaluate_actions at 0x7eed58d5c790>", "get_distribution": "<function ActorCriticPolicy.get_distribution at 0x7eed58d5c820>", "predict_values": "<function ActorCriticPolicy.predict_values at 0x7eed58d5c8b0>", "__abstractmethods__": "frozenset()", "_abc_impl": "<_abc._abc_data object at 0x7eed58ee9400>"}, "verbose": 1, "policy_kwargs": {}, "num_timesteps": 2015232, "_total_timesteps": 2000000, "_num_timesteps_at_start": 0, "seed": null, "action_noise": null, "start_time": 1711827161506045483, "learning_rate": 0.0003, "tensorboard_log": null, "_last_obs": {":type:": "<class 'numpy.ndarray'>", ":serialized:": "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"}, "_last_episode_starts": {":type:": "<class 'numpy.ndarray'>", ":serialized:": "gAWVgwAAAAAAAACMEm51bXB5LmNvcmUubnVtZXJpY5SMC19mcm9tYnVmZmVylJOUKJYQAAAAAAAAAAAAAAAAAAAAAAAAAAAAAACUjAVudW1weZSMBWR0eXBllJOUjAJiMZSJiIeUUpQoSwOMAXyUTk5OSv////9K/////0sAdJRiSxCFlIwBQ5R0lFKULg=="}, "_last_original_obs": null, "_episode_num": 0, "use_sde": false, "sde_sample_freq": -1, "_current_progress_remaining": -0.007616000000000067, "_stats_window_size": 100, "ep_info_buffer": {":type:": "<class 'collections.deque'>", ":serialized:": "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"}, "ep_success_buffer": {":type:": "<class 'collections.deque'>", ":serialized:": "gAWVIAAAAAAAAACMC2NvbGxlY3Rpb25zlIwFZGVxdWWUk5QpS2SGlFKULg=="}, "_n_updates": 984, "observation_space": {":type:": "<class 'gymnasium.spaces.box.Box'>", ":serialized:": "gAWVdgIAAAAAAACMFGd5bW5hc2l1bS5zcGFjZXMuYm94lIwDQm94lJOUKYGUfZQojAVkdHlwZZSMBW51bXB5lIwFZHR5cGWUk5SMAmY0lImIh5RSlChLA4wBPJROTk5K/////0r/////SwB0lGKMDWJvdW5kZWRfYmVsb3eUjBJudW1weS5jb3JlLm51bWVyaWOUjAtfZnJvbWJ1ZmZlcpSTlCiWCAAAAAAAAAABAQEBAQEBAZRoCIwCYjGUiYiHlFKUKEsDjAF8lE5OTkr/////Sv////9LAHSUYksIhZSMAUOUdJRSlIwNYm91bmRlZF9hYm92ZZRoESiWCAAAAAAAAAABAQEBAQEBAZRoFUsIhZRoGXSUUpSMBl9zaGFwZZRLCIWUjANsb3eUaBEoliAAAAAAAAAAAAC0wgAAtMIAAKDAAACgwNsPScAAAKDAAAAAgAAAAICUaAtLCIWUaBl0lFKUjARoaWdolGgRKJYgAAAAAAAAAAAAtEIAALRCAACgQAAAoEDbD0lAAACgQAAAgD8AAIA/lGgLSwiFlGgZdJRSlIwIbG93X3JlcHKUjFtbLTkwLiAgICAgICAgLTkwLiAgICAgICAgIC01LiAgICAgICAgIC01LiAgICAgICAgIC0zLjE0MTU5MjcgIC01LgogIC0wLiAgICAgICAgIC0wLiAgICAgICBdlIwJaGlnaF9yZXBylIxTWzkwLiAgICAgICAgOTAuICAgICAgICAgNS4gICAgICAgICA1LiAgICAgICAgIDMuMTQxNTkyNyAgNS4KICAxLiAgICAgICAgIDEuICAgICAgIF2UjApfbnBfcmFuZG9tlE51Yi4=", "dtype": "float32", "bounded_below": "[ True True True True True True True True]", "bounded_above": "[ True True True True True True True True]", "_shape": [8], "low": "[-90. -90. -5. -5. -3.1415927 -5.\n -0. -0. ]", "high": "[90. 90. 5. 5. 3.1415927 5.\n 1. 1. ]", "low_repr": "[-90. -90. -5. -5. -3.1415927 -5.\n -0. -0. ]", "high_repr": "[90. 90. 5. 5. 3.1415927 5.\n 1. 1. ]", "_np_random": null}, "action_space": {":type:": "<class 'gymnasium.spaces.discrete.Discrete'>", ":serialized:": "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", "n": "4", "start": "0", "_shape": [], "dtype": "int64", "_np_random": "Generator(PCG64)"}, "n_envs": 16, "n_steps": 1024, "gamma": 0.999, "gae_lambda": 0.98, "ent_coef": 0.01, "vf_coef": 0.5, "max_grad_norm": 0.5, "batch_size": 64, "n_epochs": 8, "clip_range": {":type:": "<class 'function'>", ":serialized:": "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"}, "clip_range_vf": null, "normalize_advantage": true, "target_kl": null, "lr_schedule": {":type:": "<class 'function'>", ":serialized:": "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"}, "system_info": {"OS": "Linux-6.1.58+-x86_64-with-glibc2.35 # 1 SMP PREEMPT_DYNAMIC Sat Nov 18 15:31:17 UTC 2023", "Python": "3.10.12", "Stable-Baselines3": "2.0.0a5", "PyTorch": "2.2.1+cu121", "GPU Enabled": "True", "Numpy": "1.25.2", "Cloudpickle": "2.2.1", "Gymnasium": "0.28.1", "OpenAI Gym": "0.25.2"}}
ppo-LunarLander-v3.zip ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:0bae51936e21cc8834e56f86f7ac44f053e75c770a3044f6c5da8c0a42ed6d3d
3
+ size 148238
ppo-LunarLander-v3/_stable_baselines3_version ADDED
@@ -0,0 +1 @@
 
 
1
+ 2.0.0a5
ppo-LunarLander-v3/data ADDED
@@ -0,0 +1,99 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "policy_class": {
3
+ ":type:": "<class 'abc.ABCMeta'>",
4
+ ":serialized:": "gAWVOwAAAAAAAACMIXN0YWJsZV9iYXNlbGluZXMzLmNvbW1vbi5wb2xpY2llc5SMEUFjdG9yQ3JpdGljUG9saWN5lJOULg==",
5
+ "__module__": "stable_baselines3.common.policies",
6
+ "__doc__": "\n Policy class for actor-critic algorithms (has both policy and value prediction).\n Used by A2C, PPO and the likes.\n\n :param observation_space: Observation space\n :param action_space: Action space\n :param lr_schedule: Learning rate schedule (could be constant)\n :param net_arch: The specification of the policy and value networks.\n :param activation_fn: Activation function\n :param ortho_init: Whether to use or not orthogonal initialization\n :param use_sde: Whether to use State Dependent Exploration or not\n :param log_std_init: Initial value for the log standard deviation\n :param full_std: Whether to use (n_features x n_actions) parameters\n for the std instead of only (n_features,) when using gSDE\n :param use_expln: Use ``expln()`` function instead of ``exp()`` to ensure\n a positive standard deviation (cf paper). It allows to keep variance\n above zero and prevent it from growing too fast. In practice, ``exp()`` is usually enough.\n :param squash_output: Whether to squash the output using a tanh function,\n this allows to ensure boundaries when using gSDE.\n :param features_extractor_class: Features extractor to use.\n :param features_extractor_kwargs: Keyword arguments\n to pass to the features extractor.\n :param share_features_extractor: If True, the features extractor is shared between the policy and value networks.\n :param normalize_images: Whether to normalize images or not,\n dividing by 255.0 (True by default)\n :param optimizer_class: The optimizer to use,\n ``th.optim.Adam`` by default\n :param optimizer_kwargs: Additional keyword arguments,\n excluding the learning rate, to pass to the optimizer\n ",
7
+ "__init__": "<function ActorCriticPolicy.__init__ at 0x7eed58d5c280>",
8
+ "_get_constructor_parameters": "<function ActorCriticPolicy._get_constructor_parameters at 0x7eed58d5c310>",
9
+ "reset_noise": "<function ActorCriticPolicy.reset_noise at 0x7eed58d5c3a0>",
10
+ "_build_mlp_extractor": "<function ActorCriticPolicy._build_mlp_extractor at 0x7eed58d5c430>",
11
+ "_build": "<function ActorCriticPolicy._build at 0x7eed58d5c4c0>",
12
+ "forward": "<function ActorCriticPolicy.forward at 0x7eed58d5c550>",
13
+ "extract_features": "<function ActorCriticPolicy.extract_features at 0x7eed58d5c5e0>",
14
+ "_get_action_dist_from_latent": "<function ActorCriticPolicy._get_action_dist_from_latent at 0x7eed58d5c670>",
15
+ "_predict": "<function ActorCriticPolicy._predict at 0x7eed58d5c700>",
16
+ "evaluate_actions": "<function ActorCriticPolicy.evaluate_actions at 0x7eed58d5c790>",
17
+ "get_distribution": "<function ActorCriticPolicy.get_distribution at 0x7eed58d5c820>",
18
+ "predict_values": "<function ActorCriticPolicy.predict_values at 0x7eed58d5c8b0>",
19
+ "__abstractmethods__": "frozenset()",
20
+ "_abc_impl": "<_abc._abc_data object at 0x7eed58ee9400>"
21
+ },
22
+ "verbose": 1,
23
+ "policy_kwargs": {},
24
+ "num_timesteps": 2015232,
25
+ "_total_timesteps": 2000000,
26
+ "_num_timesteps_at_start": 0,
27
+ "seed": null,
28
+ "action_noise": null,
29
+ "start_time": 1711827161506045483,
30
+ "learning_rate": 0.0003,
31
+ "tensorboard_log": null,
32
+ "_last_obs": {
33
+ ":type:": "<class 'numpy.ndarray'>",
34
+ ":serialized:": "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"
35
+ },
36
+ "_last_episode_starts": {
37
+ ":type:": "<class 'numpy.ndarray'>",
38
+ ":serialized:": "gAWVgwAAAAAAAACMEm51bXB5LmNvcmUubnVtZXJpY5SMC19mcm9tYnVmZmVylJOUKJYQAAAAAAAAAAAAAAAAAAAAAAAAAAAAAACUjAVudW1weZSMBWR0eXBllJOUjAJiMZSJiIeUUpQoSwOMAXyUTk5OSv////9K/////0sAdJRiSxCFlIwBQ5R0lFKULg=="
39
+ },
40
+ "_last_original_obs": null,
41
+ "_episode_num": 0,
42
+ "use_sde": false,
43
+ "sde_sample_freq": -1,
44
+ "_current_progress_remaining": -0.007616000000000067,
45
+ "_stats_window_size": 100,
46
+ "ep_info_buffer": {
47
+ ":type:": "<class 'collections.deque'>",
48
+ ":serialized:": "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"
49
+ },
50
+ "ep_success_buffer": {
51
+ ":type:": "<class 'collections.deque'>",
52
+ ":serialized:": "gAWVIAAAAAAAAACMC2NvbGxlY3Rpb25zlIwFZGVxdWWUk5QpS2SGlFKULg=="
53
+ },
54
+ "_n_updates": 984,
55
+ "observation_space": {
56
+ ":type:": "<class 'gymnasium.spaces.box.Box'>",
57
+ ":serialized:": "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",
58
+ "dtype": "float32",
59
+ "bounded_below": "[ True True True True True True True True]",
60
+ "bounded_above": "[ True True True True True True True True]",
61
+ "_shape": [
62
+ 8
63
+ ],
64
+ "low": "[-90. -90. -5. -5. -3.1415927 -5.\n -0. -0. ]",
65
+ "high": "[90. 90. 5. 5. 3.1415927 5.\n 1. 1. ]",
66
+ "low_repr": "[-90. -90. -5. -5. -3.1415927 -5.\n -0. -0. ]",
67
+ "high_repr": "[90. 90. 5. 5. 3.1415927 5.\n 1. 1. ]",
68
+ "_np_random": null
69
+ },
70
+ "action_space": {
71
+ ":type:": "<class 'gymnasium.spaces.discrete.Discrete'>",
72
+ ":serialized:": "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",
73
+ "n": "4",
74
+ "start": "0",
75
+ "_shape": [],
76
+ "dtype": "int64",
77
+ "_np_random": "Generator(PCG64)"
78
+ },
79
+ "n_envs": 16,
80
+ "n_steps": 1024,
81
+ "gamma": 0.999,
82
+ "gae_lambda": 0.98,
83
+ "ent_coef": 0.01,
84
+ "vf_coef": 0.5,
85
+ "max_grad_norm": 0.5,
86
+ "batch_size": 64,
87
+ "n_epochs": 8,
88
+ "clip_range": {
89
+ ":type:": "<class 'function'>",
90
+ ":serialized:": "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"
91
+ },
92
+ "clip_range_vf": null,
93
+ "normalize_advantage": true,
94
+ "target_kl": null,
95
+ "lr_schedule": {
96
+ ":type:": "<class 'function'>",
97
+ ":serialized:": "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"
98
+ }
99
+ }
ppo-LunarLander-v3/policy.optimizer.pth ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:d1039e096e8faea38990e34540438e6086cd4944fc77c939f4e9a3f050a35a1c
3
+ size 88362
ppo-LunarLander-v3/policy.pth ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:e866ceba05fb88965632a04cc00dd92206ac62eff02c3b1ed1ad5aa12efd9949
3
+ size 43762
ppo-LunarLander-v3/pytorch_variables.pth ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:0c35cea3b2e60fb5e7e162d3592df775cd400e575a31c72f359fb9e654ab00c5
3
+ size 864
ppo-LunarLander-v3/system_info.txt ADDED
@@ -0,0 +1,9 @@
 
 
 
 
 
 
 
 
 
 
1
+ - OS: Linux-6.1.58+-x86_64-with-glibc2.35 # 1 SMP PREEMPT_DYNAMIC Sat Nov 18 15:31:17 UTC 2023
2
+ - Python: 3.10.12
3
+ - Stable-Baselines3: 2.0.0a5
4
+ - PyTorch: 2.2.1+cu121
5
+ - GPU Enabled: True
6
+ - Numpy: 1.25.2
7
+ - Cloudpickle: 2.2.1
8
+ - Gymnasium: 0.28.1
9
+ - OpenAI Gym: 0.25.2
replay.mp4 CHANGED
Binary files a/replay.mp4 and b/replay.mp4 differ
 
results.json CHANGED
@@ -1 +1 @@
1
- {"mean_reward": 256.44691247676053, "std_reward": 18.73032177596516, "is_deterministic": true, "n_eval_episodes": 10, "eval_datetime": "2024-03-30T16:56:17.657541"}
 
1
+ {"mean_reward": 289.50370461296706, "std_reward": 16.81361146736249, "is_deterministic": true, "n_eval_episodes": 10, "eval_datetime": "2024-03-30T20:14:35.459778"}